CN118614926A - A wearable device for emotion recognition based on voiceprint learning and its preparation method - Google Patents

Abstract

The present invention provides an emotion recognition wearable device based on voiceprint learning and a preparation method thereof, the preparation method comprising the following steps: placing various functional units on the surface of a flexible piezoelectric sensor assembled from a piezoelectric film, and connecting the various parts with electrode wires; spin coating the packaging material on the surface of the flexible piezoelectric sensor, and curing it in an oven. The flexible piezoelectric sensor comprises a hydrogel layer that can adhere to the skin to achieve the wearable function of the device. The device collects the voice signal generated by the throat, amplifies, denoises, filters, and converts analog to digital, and transmits it to the mobile phone end through a Bluetooth module. The mobile phone end pre-processes the voice signal data through a bandpass filter, then performs a fast Fourier transform on the sound frame, converts the time domain waveform into a Mel spectrum, and sends it to a convolutional neural network classifier, and then passes through a maximum pooling layer in a hidden state; finally, through a linear layer and a fully connected layer, emotion recognition is achieved.

Description

A wearable device for emotion recognition based on voiceprint learning and its preparation method

Technical Field

The present invention relates to the technical field of patient emotion monitoring, and in particular to an emotion recognition wearable device based on voiceprint learning and a preparation method thereof.

Background Art

As one of the important indicators of mental health, emotions play a key role in daily work and life. For patients with mental illnesses such as anxiety, depression, and affective disorders, recording emotional states helps monitor and treat mental illnesses and provides an important basis for the patient's rehabilitation effect.

With the development of artificial intelligence, analyzing and inferring the speaker's emotional state by analyzing individual voice signals and extracting sound features - voiceprints has become an important research direction. Through voiceprint learning, a model that can accurately describe and distinguish the voice features of different individuals can be established to identify and infer the speaker's current emotional state, such as joy, anger, sadness, etc.

Voiceprint learning requires the collection of individual voice signals. Some common wearable devices used to collect human voice signals, such as smart headphones and glasses, are easily interfered by environmental noise, which affects the quality of voice signals and reduces the accuracy of emotion recognition.

Summary of the invention

The purpose of the present invention is to provide an emotion recognition wearable device based on voiceprint learning and a preparation method thereof, which can collect an individual's own voice signal to achieve simple, convenient and accurate emotion recognition, so as to solve the problems encountered in the above-mentioned background technology.

To achieve the above object, the technical solution of the present invention is as follows:

An emotion recognition wearable device based on voiceprint learning includes a flexible piezoelectric sensor and a signal processing module, a power module, and a Bluetooth module arranged on the outer surface of the flexible piezoelectric sensor. The power module is respectively connected to the signal processing module and the Bluetooth module to supply power to them, and the flexible piezoelectric sensor is connected to the signal processing module. The signal processing module, the power module, and the Bluetooth module are placed on the upper surface of the flexible piezoelectric sensor, and the modules are interconnected with wires.

The power module is connected to the Bluetooth module and sends data to the mobile terminal, which recognizes and displays the user's emotions. The power module uses a rechargeable button battery or polymer lithium battery and is equipped with a Type-C charging interface.

The flexible piezoelectric sensor collects the voice signal generated by the throat vibration and transmits it to the signal processing module, which performs preliminary processing on the voice signal and transmits the voice data to the mobile phone through the Bluetooth module.

During manufacturing, the emotion recognition wearable device also includes a packaging layer, through which the signal processing module, the power module, and the Bluetooth module are integrated on the surface of the flexible piezoelectric sensor.

The flexible piezoelectric sensor includes two upper and lower electrode layers and a middle piezoelectric layer. Specifically, the flexible piezoelectric sensor includes a piezoelectric film, a single-sided conductive electrode sheet and a mechanical interlocking electrode. The piezoelectric film is located between the electrode sheet and the mechanical interlocking electrode, and the conductive side of the electrode sheet and the mechanical interlocking electrode is attached to the piezoelectric film.

Manufacturing method of mechanical interlocking electrodes: Fibers are prepared by spinning, and the fiber material is at least one of polyurethane, polyester, polypropylene, and polyamide. Furthermore, an electrode layer is prepared on the upper surface of the fiber by evaporation, spin coating, etc. A hydrogel precursor is cast on the other side of the fiber, and thermally cured to obtain a hydrogel electrode with a mechanical interlocking structure. The hydrogel and the fiber form a mechanical interlocking area, and the hydrogel layer has a high degree of adhesion and can be attached to the skin, thereby achieving the wearability of the device.

The signal processing module includes a preamplifier circuit, a 50Hz notch circuit, a bandpass filter circuit, and an A/D conversion circuit; the preamplifier circuit is used to amplify the voice signal; the 50Hz notch circuit is used to filter out power frequency interference; the bandpass filter circuit is used to limit the frequency range of the voice signal; the A/D conversion circuit is used to perform analog-to-digital conversion on the voice signal; the power module is used to supply energy to all circuits in the signal processing module; and the Bluetooth module is used to send the collected voice data to the mobile phone.

A method for preparing an emotion recognition wearable device based on voiceprint learning comprises the following steps:

A piezoelectric film is prepared by using a piezoelectric material, and is assembled with an electrode sheet and a mechanically interlocked electrode into a flexible piezoelectric sensor, wherein the flexible piezoelectric sensor is used to convert the throat vibration of the user when speaking into an electrical signal;

Various functional units are placed on the surface of the flexible piezoelectric sensor, including: a signal processing module, a power module, and a Bluetooth module; electrode wires are arranged on the flexible piezoelectric sensor according to corresponding circuits to connect various functional units;

Insulating and biocompatible organic materials are spin-coated on the surface of the flexible piezoelectric sensor to encapsulate each functional unit and electrode wire.

Furthermore, the piezoelectric material is made of at least one of polyvinylidene fluoride, fluorinated polymer, polylactic acid, polyacrylonitrile, and cellulose, a certain concentration of filler is added, dissolved in a solvent in a certain proportion and magnetically stirred to obtain a suspension with uniformly dispersed particles, and the piezoelectric film is obtained by electrospinning or spin coating.

Among them, the manufacturing method of the piezoelectric film is: the piezoelectric material is prepared into a solution of a certain concentration, and a uniform piezoelectric film with a thickness of about 100 microns is prepared by spin coating, spraying, stretching, calendering, spinning and polarization.

Furthermore, in order to improve the piezoelectric performance of the piezoelectric sensor, a simple and effective method is adopted, that is, adding a certain concentration of additives or fillers to the piezoelectric material. The filler is used to improve the piezoelectric conversion efficiency of the flexible piezoelectric sensor, and the filler is one or more of metal nanoparticles, metal oxides, piezoelectric ceramics, and nano zinc oxide particles.

The prepared piezoelectric film is sandwiched between an electrode sheet and a mechanical interlocking electrode to assemble a piezoelectric sensor. The electrode sheet material can be a conductive tape or a conductive copper sheet. The electrode sheet and the mechanical interlocking electrode are conductive on one side, that is, the side in contact with the piezoelectric film is conductive, and the other side is non-conductive.

An emotion recognition wearable device based on voiceprint learning, the algorithm for realizing emotion recognition includes the following steps:

The flexible piezoelectric sensor is used to record multiple speech signals, each of which is manually classified and labeled with four emotion labels: anger, calm, happiness and sadness. During training, the ratio of the training set to the test set is set to 8:2.

Before training the model, the speech signal data of four different emotional expressions were preprocessed through a bandpass filter to remove extremely low or high frequency signals. The filtered signal was first split into small frames through a Hanning window, and then the sound frame was subjected to fast Fourier transform and 80-band Mel filtering to convert the time domain waveform into a Mel spectrogram.

The size of the Hanning window is 1024 milliseconds and the jump length is 320 milliseconds.

The 80-channel Mel-spectrogram is fed into the convolutional neural network (CNN) classifier and then passed through a max pooling layer in the hidden state to reduce computational cost and variance. The classifier consists of 5 layers of convolutional neural network (CNN), and the convolution kernel size of each layer is [1,1,3,3,5].

Finally, the linear layer and the fully connected layer are used to project emotions as the final classification result to achieve emotion recognition.

Compared with the prior art, the beneficial effect of the present invention is that the present wearable emotion recognition device collects throat voice signals through a flexible piezoelectric sensor, transmits the data to the mobile phone through a series of circuits, and then performs emotion recognition through a trained voiceprint learning method. Therefore, compared with the prior art, the present device can collect an individual's own voice signals to achieve simple, convenient and accurate emotion recognition.

BRIEF DESCRIPTION OF THE DRAWINGS

The disclosure of the present invention is described with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. In the accompanying drawings, the same reference numerals are used to refer to the same components. Among them:

FIG1 is a system block diagram of an emotion recognition wearable device based on voiceprint learning;

FIG2 is a schematic diagram of the working of an emotion recognition wearable device based on voiceprint learning;

FIG3 is a schematic diagram of the structure of an emotion recognition wearable device based on voiceprint learning;

FIG4 is a schematic diagram of the integrated packaging of an emotion recognition wearable device based on voiceprint learning;

FIG5 is a schematic diagram of the structure of a flexible piezoelectric sensor according to an embodiment of the present invention;

FIG6 is a schematic diagram of a machine learning model for an emotion recognition wearable device based on voiceprint learning;

FIG7 is a Fourier infrared spectrum of a piezoelectric film according to an embodiment of the present invention;

FIG8 is a diagram of an example of a voice signal collected by the flexible piezoelectric sensor introduced in an embodiment of the present invention;

FIG. 9 is an example of a Mel spectrum diagram collected by the flexible piezoelectric sensor introduced in an embodiment of the present invention.

Explanations in the figure: 1. A wearable device for emotion recognition based on voiceprint learning; 2. Flexible piezoelectric sensor; 21-piezoelectric film; 22-electrode sheet; 23-mechanical interlocking electrode; 231-electrode layer; 232-mechanical interlocking area; 233-hydrogel layer; 3. Signal processing module; 4. Power module; 5. Bluetooth module; 6. Type-C charging port; 7. Packaging layer.

DETAILED DESCRIPTION

In order to make the technical means, creative features, objectives and effects of the present invention easy to understand, the present invention is now further described in detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the relevant components of the present invention.

According to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific implementation modes and the accompanying drawings are only exemplary descriptions of the technical solution of the present invention, and should not be regarded as the whole of the present invention or as a limitation or restriction to the technical solution of the present invention.

The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

Embodiment 1, please refer to Figures 1 and 2, an emotion recognition wearable device based on voiceprint learning, includes a flexible piezoelectric sensor 2 and a signal processing module 3, a power module 4, and a Bluetooth module 5 arranged on the outer surface of the flexible piezoelectric sensor 2, the power module 4 is respectively connected to the signal processing module 3 and the Bluetooth module 5 to power them, and the flexible piezoelectric sensor 2 is connected to the signal processing module 3. The signal processing module 3, the power module 4, and the Bluetooth module 5 are placed on the upper surface of the flexible piezoelectric sensor 2, and the modules are interconnected with wires.

The power module 4 is connected to the Bluetooth module 5 and sends data to the mobile terminal, which recognizes and displays the user's emotions. The power module uses a rechargeable button battery or a polymer lithium battery and is equipped with a Type-C charging interface 6.

The flexible piezoelectric sensor collects the voice signal generated by the throat vibration and transmits it to the signal processing module, which performs preliminary processing on the voice signal and transmits the voice data to the mobile phone through the Bluetooth module.

Embodiment 2, please refer to Figures 3 to 5. This embodiment introduces a method for preparing an emotion recognition wearable device based on voiceprint learning, which mainly includes a flexible piezoelectric sensor, a functional unit and a packaging layer arranged in sequence. Therefore, the steps of the preparation method are as follows:

Step 1: Prepare the piezoelectric film 21 by electrospinning. The piezoelectric film 21 can be a piezoelectric fiber film. A certain amount of nano zinc oxide particles are placed in a mixed solvent of acetone and dimethylformamide, and the nano zinc oxide particles are evenly dispersed in the mixed solvent by ultrasonication for two hours. Then polyvinylidene fluoride powder is added thereto, and magnetic stirring is performed at 50°C for 12 hours to obtain a spinning solution.

The spinning solution is loaded into a 10 ml syringe, and then a 21G needle is connected to the syringe needle. The syringe is then mounted on a syringe pump to provide a constant flow rate of 0.5 ml per hour. Electrospinning is performed at a voltage of 15 kV, and the fixed distance between the spinning head and the collector is 15 cm. A rotating drum collects the piezoelectric film 21 at a speed of 100 revolutions per minute. The Fourier infrared spectrum of the piezoelectric film 21 is shown in Figure 7, which contains a crystalline phase of polyvinylidene fluoride.

The mechanical interlocking electrode 23 is prepared by spinning fibers, and the fiber material is at least one of polyurethane, polyester, polypropylene, and polyamide. For example, in the implementation, a certain amount of polyurethane is dissolved in a mixed solvent of acetone and dimethylformamide, and stirred at room temperature for 24 hours. Then, the mixed solution is spun into polyurethane fibers at an electrospinning voltage of 20 kV.

A layer of silver electrode is prepared on the surface of the polyurethane fiber by evaporation. Then a hydrogel precursor is cast on the other side of the fiber and cured at 50°C for 2 hours to finally obtain a mechanically interlocked electrode. The hydrogel precursor consists of a certain concentration of acrylamide, sodium alginate, calcium carbonate nanopowder and tetramethylethylenediamine. An electrode layer 231 is prepared on the upper surface of the fiber by evaporation, spin coating and other methods. A hydrogel precursor is cast on the other side of the fiber and thermally cured to obtain a hydrogel electrode with a mechanically interlocking structure. The hydrogel and the fiber form a mechanically interlocking region 232, and the hydrogel layer 233 has a high degree of adhesion and can be attached to the skin, thereby achieving the wearability of the device.

Step 2: Prepare a flexible piezoelectric sensor, as shown in Figure 5. The prepared piezoelectric fiber film is assembled into a sandwich structure with a single-sided conductive sheet and a mechanical interlocking electrode. The conductive sheet 22 can be a copper sheet, and the conductive side is attached to the piezoelectric fiber film, i.e., the piezoelectric film 21.

Step 3: As shown in FIG. 4 , the functional units are adhered to the preset positions on the surface of the flexible piezoelectric sensor 2 , and the various units are connected according to the corresponding circuits using conductive silver paste.

The functional unit includes a signal processing module, a power module, and a Bluetooth module. The signal processing module 3 includes a preamplifier circuit, a 50Hz notch circuit, a bandpass filter circuit, and an A/D conversion circuit. The signal processing module 3 further processes the voice signal collected by the flexible piezoelectric sensor, and transmits the data to the mobile phone through the Bluetooth module 5, performs voiceprint learning on the voice data, and finally realizes emotion recognition.

The entire device is powered by the power module 4 and is equipped with the Type-C charging port 6 charging interface.

It should be noted that the upper and lower electrodes of the flexible piezoelectric sensor 2 need to be connected to the signal processing module so that the voice signal collected by the sensor enters the signal processing module.

Step 4: Coat a layer of the encapsulation layer 7 on the surface of the device prepared above to protect each unit and circuit.

A specific method is: the encapsulation layer material is polydimethylsiloxane, and it is mixed with a cross-linking agent in a ratio of 10:1, stirred with a glass rod for 5 minutes to make it evenly mixed, and then the bubbles in the solution are removed by a centrifuge for subsequent use. The prepared polydimethylsiloxane is spin-coated on the surface of the device and cured in an oven at 60°C for 5 hours.

In this embodiment, a flexible piezoelectric sensor is prepared, and various functional units are integrated on the surface of the piezoelectric sensor, and further packaged to obtain the wearable device 1. As shown in FIG2 , the device can convert the vibration of the vocal cord into a voltage signal, amplify, denoise, filter and convert the signal into analog-to-digital through a signal processing module, and then transmit the signal to the mobile phone through a Bluetooth module for emotion recognition.

Embodiment 3, this embodiment introduces another method for preparing an emotion recognition wearable device based on voiceprint learning, which also includes a flexible piezoelectric sensor, a functional unit and a packaging layer arranged in sequence, and the specific steps are as follows:

Step 1: uniformly disperse the filler in the solvent by ultrasound, add the piezoelectric material and stir evenly. The filler can be one or more of metal nanoparticles, metal oxides, and piezoelectric ceramics. The piezoelectric material can be at least one of polyvinylidene fluoride, fluorinated polymer, polylactic acid, polyacrylonitrile, and cellulose.

The mixed solution was spin-coated on a glass substrate and heat-treated in a drying oven at 60° C. for 2 hours to obtain a piezoelectric film.

It should be noted that the piezoelectric film needs to be polarized at high voltage to have piezoelectric properties.

Step 2: Evaporate electrodes on both sides of the polarized piezoelectric film. The electrode materials can be conductive metals such as gold, silver, and copper. Alternatively, conductive polymers can be sprayed on both sides of the piezoelectric film to obtain a flexible piezoelectric sensor. Then, a polyacrylamide hydrogel precursor is cast on one side of the flexible piezoelectric sensor and cured at 50°C for 2 hours to obtain a polyacrylamide hydrogel, so that the entire device can adhere to the skin surface.

Step 3: Add a 10 micron thick flexible substrate on the flexible piezoelectric sensor 2 for stacking various functional units. The substrate material can be one of silica gel, polyethylene terephthalate, and polyurethane. Draw a conductive circuit on the flexible substrate in advance by inkjet printing or thermal evaporation, and then connect each functional unit to the circuit according to the preset position.

Step 4: Encapsulate the surface of the device. On the one hand, it fixes each functional unit to make it integrated and improve the mechanical strength. On the other hand, it prevents the device from direct contact with the outside world and protects each functional unit.

Embodiment 4: This embodiment introduces an emotion recognition wearable device based on voiceprint learning, which mainly includes a flexible piezoelectric sensor, a functional unit and an emotion recognition algorithm.

The flexible piezoelectric sensor is obtained by the preparation method described in Example 1 or Example 2. The flexible piezoelectric sensor can convert the mechanical vibration of the vocal cord through the skin into a voltage signal. When a person speaks, the voltage signal is a voice signal.

The functional unit includes a signal processing module, a power module, and a Bluetooth module, which are integrated on the surface of the flexible piezoelectric sensor through a packaging layer. Each functional unit is connected through an electrode wire.

The flexible piezoelectric sensor collects individual voice signals in real time and transmits the signals to the signal processing module to amplify, denoise, filter and convert the signals into analog-to-digital signals, and then transmits the data to the mobile phone via the Bluetooth module.

The principle diagram of the machine learning model of the emotion recognition wearable device is shown in FIG6 . The emotion recognition algorithm mainly includes the following steps:

The above equipment is used to collect speech signals with different emotions in advance. As shown in Figure 8, each signal is manually classified and labeled with four emotion labels: anger, calm, happy and sad. The ratio of the training set to the test set is set to 8:2. The speech signal data of the four different emotional expressions are preprocessed by a bandpass filter and divided into small frames by a Hanning window. Then the sound frame is fast Fourier transformed and 80-band Mel filter is performed to convert the time domain waveform into a Mel spectrogram, as shown in Figure 9. The 80-channel Mel spectrogram is sent to the convolutional neural network (CNN) classifier for emotion recognition. The classifier consists of 5 layers of CNN, and the convolution kernel size of each layer is [1,1,3,3,5]. Then, the maximum pooling layer is used to reduce the number of features in the hidden state. Finally, the linear layer and the fully connected layer are used, which are responsible for the emotion projection as the final classification result.

The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims (10)

1. An emotion recognition wearable device based on voiceprint learning, characterized in that it comprises a flexible piezoelectric sensor (2) and a signal processing module (3), a power module (4), and a Bluetooth module (5) arranged on the outer surface of the flexible piezoelectric sensor (2), wherein the power module (4) is respectively connected to the signal processing module (3) and the Bluetooth module (5) to supply power to them; the flexible piezoelectric sensor (2) is connected to the signal processing module (3), the power module (4) is connected to the Bluetooth module (5), and data is sent to a mobile terminal, and the user's emotions are recognized and displayed through the mobile terminal. 2. According to claim 1, an emotion recognition wearable device based on voiceprint learning is characterized in that it also includes a packaging layer (7), through which the signal processing module (3), the power module (4), and the Bluetooth module (5) are integrated on the surface of the flexible piezoelectric sensor (2) to form an integrated structure. 3. According to claim 1, an emotion recognition wearable device based on voiceprint learning is characterized in that: the flexible piezoelectric sensor (2) includes a piezoelectric film (21), a single-sided conductive electrode sheet (22) and a mechanical interlocking electrode (23), the piezoelectric film (21) is located between the electrode sheet (22) and the mechanical interlocking electrode (23), and the conductive side of the electrode sheet (22) is attached to the piezoelectric film (21). 4. The wearable device for emotion recognition based on voiceprint learning according to claim 3, characterized in that: the mechanical interlocking electrode (23) comprises an electrode layer (231), a mechanical interlocking region (232) and a hydrogel layer (233). The electrode layer (231) is attached to the piezoelectric film (21), and the hydrogel layer (233) has mechanical softness and high skin adhesion, and the mechanical interlocking region (232) is distributed throughout the hydrogel layer (233). 5. According to claim 1, an emotion recognition wearable device based on voiceprint learning is characterized in that: the signal processing module includes a preamplifier circuit, a 50Hz notch circuit, a bandpass filter circuit, and an A/D conversion circuit; the preamplifier circuit is used to amplify the voice signal; the 50Hz notch circuit is used to filter out power frequency interference; the bandpass filter circuit is used to limit the frequency range of the voice signal; the A/D conversion circuit is used to perform analog-to-digital conversion on the voice signal; the power module is used to supply energy to all circuits in the signal processing module; the Bluetooth module is used to send the collected voice data to the mobile phone. 6. A method for preparing a wearable device for emotion recognition based on voiceprint learning according to any one of claims 1 to 5, characterized in that it comprises the following steps: A piezoelectric film is prepared by using a piezoelectric material, and is assembled with an electrode sheet into a flexible piezoelectric sensor, wherein the flexible piezoelectric sensor is used to convert the throat vibration of the user when speaking into an electrical signal; Various functional units are placed on the surface of the flexible piezoelectric sensor, including: a signal processing module, a power module, and a Bluetooth module; electrode wires are arranged on the flexible piezoelectric sensor according to corresponding circuits to connect various functional units; Insulating and biocompatible organic materials are spin-coated on the surface of the flexible piezoelectric sensor to encapsulate each functional unit and electrode wire. 7. A method for preparing a wearable device for emotion recognition based on voiceprint learning according to claim 6, characterized in that: the piezoelectric material adopts at least one of polyvinylidene fluoride, fluorinated polymer, polylactic acid, polyacrylonitrile, and cellulose, a certain concentration of filler is added, dissolved in a solvent according to a certain proportion and magnetically stirred to obtain a suspension with uniformly dispersed particles, and the piezoelectric film is obtained by electrospinning or spin coating. 8. According to the method for preparing a wearable device for emotion recognition based on voiceprint learning in claim 7, it is characterized in that: the filler is one or more of metal nanoparticles, metal oxides, piezoelectric ceramics, and nano zinc oxide particles; the filler is used to improve the piezoelectric conversion efficiency of the flexible piezoelectric sensor. 9. The method for preparing a wearable device for emotion recognition based on voiceprint learning according to claim 6, wherein the algorithm for implementing emotion recognition comprises the following steps: Multiple speech signals were recorded using the flexible piezoelectric sensor, and each signal was manually classified and labeled with four emotion labels: angry, calm, happy, and sad; The speech signal data is preprocessed through a bandpass filter to remove extremely low or high frequency signals, and then divided into small frames through a Hanning window. Then, the sound frame is subjected to fast Fourier transform and 80-band Mel filtering to convert the time domain waveform into a Mel spectrogram. The 80-channel Mel-spectrogram is fed into the classifier of the convolutional neural network and then passed through a max pooling layer in the hidden state to reduce computational cost and variance; Finally, the linear layer and the fully connected layer are used to project emotions as the final classification result to achieve emotion recognition. 10. The method for preparing a wearable device for emotion recognition based on voiceprint learning according to claim 9 is characterized in that: the size of the Hanning window is 1024 milliseconds and the jump length is 320 milliseconds; the classifier is composed of a 5-layer convolutional neural network, and the convolution kernel size of each layer is [1,1,3,3,5].